How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

mem:search - Prompt - OpenSmartRoute

Name: mem:search
Author: Xsaven

Prompt file imported from Xsaven/vector-memory-mcp (.claude/commands/mem/search.md). Fill in {{arguments}} before use. Copyright stays with the author.

Input

STORE-AS($RAW_INPUT = {{arguments}}) STORE-AS($SEARCH_QUERY = {search query extracted from $RAW_INPUT})

Role

Semantic memory search utility that queries vector storage with optional filters and displays formatted results with similarity scores.

Workflow step1

STEP 1 - Parse Arguments for Query and Filters

format-1: Simple query: /mem:search "authentication patterns"
format-2: With filters: /mem:search query="auth" category=code-solution limit=20
format-3: With tags: /mem:search query="api" tags=laravel,php
extract: STORE-AS($QUERY = {parse query from $RAW_INPUT, required})
filters: STORE-AS($FILTERS = {parse category?, limit?, offset?, tags? from $RAW_INPUT})
defaults: Defaults: limit=10, offset=0
output: STORE-AS($PARAMS = {query: $QUERY, ...$FILTERS})

Workflow step2

STEP 2 - Execute Semantic Search

search: mcp__vector-memory__search_memories('STORE-GET($PARAMS)')
store: STORE-AS($RESULTS = search results array)

Workflow step3

STEP 3 - Handle Empty Results

check: IF(STORE-GET($RESULTS) is empty) → Display: "No memories found for: {query}" → Suggest: "Try broader search terms" → Suggest: "Remove category/tag filters" → Suggest: "Use /mem:list to see recent memories" → END-IF

Workflow step4

STEP 4 - Format and Display Results

header: Display: "--- Memory Search Results ---"
meta: Display: "Query: {query} | Found: {count} | Category: {category or all}"
list: FOREACH(memory in STORE-GET($RESULTS)) → Display: "#{id} [{category}] (similarity: {score})" → Display: " {content_preview} (first 100 chars)" → Display: " Tags: {tags} | Accessed: {access_count}x" → END-FOREACH
pagination: IF(more results available (total > limit + offset)) → Display: "More results available. Use offset={next_offset} to see more" → END-IF

Output format

Result display format

--- Memory Search Results ---
Query: "auth patterns" | Found: 5 | Category: code-solution
#{id} [{category}] (similarity: 0.85)
Content preview here...
Tags: php, laravel | Accessed: 3x
More results available. Use offset=10 to see more

Similarity guide

Similarity score interpretation

0.90-1.00: Highly relevant, almost exact match
0.75-0.89: Relevant, good semantic match
0.50-0.74: Somewhat related, partial match
< 0.50: Weak match, may not be useful

Filter examples

Supported filter combinations

/mem:search "query" → simple search
/mem:search query="auth" category=bug-fix → filtered by category
/mem:search query="api" tags=laravel → filtered by tag
/mem:search query="cache" limit=20 → more results
/mem:search query="db" offset=10 limit=10 → pagination

Install mem:search and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

<command> <meta> <id>mem:search</id> <description>Semantic search memories with optional filters</description> </meta> <execute>Searches memories using semantic similarity from {{arguments}} query. Supports filters: category, limit, offset, tags. Displays results with similarity scores.</execute> <provides>Semantic memory search with flexible filters. Displays results with similarity scores and content previews.</provides> <guidelines> # Input STORE-AS($RAW_INPUT = {{arguments}}) STORE-AS($SEARCH_QUERY = {search query extracted from $RAW_INPUT}) # Role Semantic memory search utility that queries vector storage with optional filters and displays formatted results with similarity scores. # Workflow step1 STEP 1 - Parse Arguments for Query and Filters - `format-1`: Simple query: /mem:search "authentication patterns" - `format-2`: With filters: /mem:search query="auth" category=code-solution limit=20 - `format-3`: With tags: /mem:search query="api" tags=laravel,php - `extract`: STORE-AS($QUERY = {parse query from $RAW_INPUT, required}) - `filters`: STORE-AS($FILTERS = {parse category?, limit?, offset?, tags? from $RAW_INPUT}) - `defaults`: Defaults: limit=10, offset=0 - `output`: STORE-AS($PARAMS = {query: $QUERY, ...$FILTERS}) # Workflow step2 STEP 2 - Execute Semantic Search - `search`: mcp__vector-memory__search_memories('STORE-GET($PARAMS)') - `store`: STORE-AS($RESULTS = search results array) # Workflow step3 STEP 3 - Handle Empty Results - `check`: IF(STORE-GET($RESULTS) is empty) → Display: "No memories found for: {query}" → Suggest: "Try broader search terms" → Suggest: "Remove category/tag filters" → Suggest: "Use /mem:list to see recent memories" → END-IF # Workflow step4 STEP 4 - Format and Display Results - `header`: Display: "--- Memory Search Results ---" - `meta`: Display: "Query: {query} | Found: {count} | Category: {category or all}" - `list`: FOREACH(memory in STORE-GET($RESULTS)) → Display: "#{id} [{category}] (similarity: {score})" → Display: " {content_preview} (first 100 chars)" → Display: " Tags: {tags} | Accessed: {access_count}x" → END-FOREACH - `pagination`: IF(more results available (total > limit + offset)) → Display: "More results available. Use offset={next_offset} to see more" → END-IF # Output format Result display format - --- Memory Search Results --- - Query: "auth patterns" | Found: 5 | Category: code-solution - #{id} [{category}] (similarity: 0.85) - Content preview here... - Tags: php, laravel | Accessed: 3x - More results available. Use offset=10 to see more # Similarity guide Similarity score interpretation - 0.90-1.00: Highly relevant, almost exact match - 0.75-0.89: Relevant, good semantic match - 0.50-0.74: Somewhat related, partial match - < 0.50: Weak match, may not be useful # Filter examples Supported filter combinations - /mem:search "query" → simple search - /mem:search query="auth" category=bug-fix → filtered by category - /mem:search query="api" tags=laravel → filtered by tag - /mem:search query="cache" limit=20 → more results - /mem:search query="db" offset=10 limit=10 → pagination </guidelines> </command>

{ "prompt": "<command>\n<meta>\n<id>mem:search</id>\n<description>Semantic search memories with optional filters</description>\n</meta>\n<execute>Searches memories using semantic similarity from {{arguments}} query. Supports filters: category, limit, offset, tags. Displays results with similarity scores.</execute>\n<provides>Semantic memory search with flexible filters. Displays results with similarity scores and content previews.</provides>\n<guidelines>\n\n# Input\nSTORE-AS($RAW_INPUT = {{arguments}})\nSTORE-AS($SEARCH_QUERY = {search query extracted from $RAW_INPUT})\n\n# Role\nSemantic memory search utility that queries vector storage with optional filters and displays formatted results with similarity scores.\n\n# Workflow step1\nSTEP 1 - Parse Arguments for Query and Filters\n- `format-1`: Simple query: /mem:search \"authentication patterns\"\n- `format-2`: With filters: /mem:search query=\"auth\" category=code-solution limit=20\n- `format-3`: With tags: /mem:search query=\"api\" tags=laravel,php\n- `extract`: STORE-AS($QUERY = {parse query from $RAW_INPUT, required})\n- `filters`: STORE-AS($FILTERS = {parse category?, limit?, offset?, tags? from $RAW_INPUT})\n- `defaults`: Defaults: limit=10, offset=0\n- `output`: STORE-AS($PARAMS = {query: $QUERY, ...$FILTERS})\n\n# Workflow step2\nSTEP 2 - Execute Semantic Search\n- `search`: mcp__vector-memory__search_memories('STORE-GET($PARAMS)')\n- `store`: STORE-AS($RESULTS = search results array)\n\n# Workflow step3\nSTEP 3 - Handle Empty Results\n- `check`: IF(STORE-GET($RESULTS) is empty) →\n Display: \"No memories found for: {query}\" → Suggest: \"Try broader search terms\" → Suggest: \"Remove category/tag filters\" → Suggest: \"Use /mem:list to see recent memories\"\n→ END-IF\n\n# Workflow step4\nSTEP 4 - Format and Display Results\n- `header`: Display: \"--- Memory Search Results ---\"\n- `meta`: Display: \"Query: {query} | Found: {count} | Category: {category or all}\"\n- `list`: FOREACH(memory in STORE-GET($RESULTS)) →\n Display: \"#{id} [{category}] (similarity: {score})\" → Display: \" {content_preview} (first 100 chars)\" → Display: \" Tags: {tags} | Accessed: {access_count}x\"\n→ END-FOREACH\n- `pagination`: IF(more results available (total > limit + offset)) →\n Display: \"More results available. Use offset={next_offset} to see more\"\n→ END-IF\n\n# Output format\nResult display format\n- --- Memory Search Results ---\n- Query: \"auth patterns\" | Found: 5 | Category: code-solution\n- #{id} [{category}] (similarity: 0.85)\n- Content preview here...\n- Tags: php, laravel | Accessed: 3x\n- More results available. Use offset=10 to see more\n\n# Similarity guide\nSimilarity score interpretation\n- 0.90-1.00: Highly relevant, almost exact match\n- 0.75-0.89: Relevant, good semantic match\n- 0.50-0.74: Somewhat related, partial match\n- < 0.50: Weak match, may not be useful\n\n# Filter examples\nSupported filter combinations\n- /mem:search \"query\" → simple search\n- /mem:search query=\"auth\" category=bug-fix → filtered by category\n- /mem:search query=\"api\" tags=laravel → filtered by tag\n- /mem:search query=\"cache\" limit=20 → more results\n- /mem:search query=\"db\" offset=10 limit=10 → pagination\n\n</guidelines>\n</command>", "variables": [ "arguments" ], "notes": "Semantic search memories with optional filters", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/Xsaven/vector-memory-mcp", "path": ".claude/commands/mem/search.md", "ref": "4cdfe093e6d68ddd46f3dcf23364cdb4351feaae", "url": "https://github.com/Xsaven/vector-memory-mcp/blob/4cdfe093e6d68ddd46f3dcf23364cdb4351feaae/.claude/commands/mem/search.md", "key": "Xsaven/vector-memory-mcp/.claude/commands/mem/search.md" } } }

mem:search

About

Input

Role

Workflow step1

Workflow step2

Workflow step3

Workflow step4

Output format

Similarity guide

Filter examples

Install mem:search and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews